Federated Learning One World Seminar (FLOW) retweeted
We just concluded our workshop with a very engaging panel at AdaptFM @ #ICML2026 on the opportunities, challenges and future directions of Adaptive Intelligence with George Kaissis, @oodgnas, @CelineLinatGT & @yin_hongxu. Thanks everyone for attending and making it a success!
Federated Learning One World Seminar (FLOW) retweeted
Excited for #ICML2026 in Seoul 🇰🇷 next week!
We’ll be presenting two papers on adaptive inference:
- FlexRank: arxiv.org/abs/2602.02680 (Spotlight)
- MoSE: arxiv.org/abs/2602.06154
We’re also organising the AdaptFM workshop (July 11):
adaptfm.gitlab.io/
See you there!
Federated Learning One World Seminar (FLOW) retweeted
📣 Call for Papers — ICOMP 2026
3rd International Conference on Computational Optimization
📍 Casablanca, Morocco · 3-6 November 2026
New Deadlines:
• Abstract: 20 June 2026
• Full paper: 5 July 2026
🔗 Submit: openreview.net/group?id=ICOM…
🌐 icomp.cc
Federated Learning One World Seminar (FLOW) retweeted
Unstructured weight #sparsity made practical.
50% unstructured weight sparsity was considered too low for real GPU speed up without specific hardware support (like @cerebras).
With @bozavlado we built MACKO-SpMV - a new matrix format + SpMV kernel to change that. 🧵
Federated Learning One World Seminar (FLOW) retweeted
Our research group at the University of Zurich (Switzerland) is seeking a PhD candidate in intersection of theory and practice in areas such as distributed optimization, federated learning, machine learning, privacy, or unlearning.
Apply here! apply.mnf.uzh.ch/positiondet…
📢: The 127th FLOW talk is on Wednesday (May 21) at **1 pm UTC.**
Please register for our mailing list: bit.ly/3WVplLU.
FLOW Calendar: bit.ly/3E9iIT4.
📢: The 126th FLOW talk is on Wednesday (April 30) at **1 pm UTC.**
Please register for our mailing list: bit.ly/3WVplLU. FLOW Calendar: bit.ly/3E9iIT4.
📢: The 125th FLOW talk is on Wednesday (April 16) at **1 pm UTC.**
Please register for our mailing list: bit.ly/3WVplLU. FLOW Calendar: bit.ly/3E9iIT4.
📢: The 124th FLOW talk is on Wednesday (April 9) at **1 pm UTC.**
Please register for our mailing list: bit.ly/3WVplLU.
FLOW Calendar: bit.ly/3E9iIT4.
📢: The 123rd FLOW talk is on Wednesday (March 26) at **1 pm UTC.**
Constantin Philippenko (INRIA) will discuss "Compressed and distributed least-squares regression: convergence rates."
Please register for our mailing list: bit.ly/3WVplLU.
1
262
Federated Learning One World Seminar (FLOW) retweeted
Fully funded PhD and MSc scholarships at MBZUAI!
📢: The 122nd FLOW talk is on Wednesday (23rd October) at **5 pm UTC**.
Ziyue Xu (@NVIDIAAI) will discuss "Federated Learning in The Age of Foundation Models."
Please register for our mailing list at bit.ly/3WVplLU.
📢: The 121st FLOW talk is on Wednesday (16th October) at **1 pm UTC**.
Eduard Gorbunov (@mbzuai) will discuss "FL Can Find Friends That Are Advantageous and Help with Low-Recourse Machine Translation."
Please register for our mailing list at bit.ly/3WVplLU.
📢: The 120th FLOW talk is on Wednesday (9th October) at **5 pm UTC**.
Nic Lane (@CaMLSys, @flwrlabs) will discuss "The Future of Large Language Models (and AI) is Federated."
Please register for our mailing list at bit.ly/3WVplLU.
📢: The 119th FLOW talk is on Wednesday (17th July) at **1 pm UTC**.
Geovani Rizk (EPFL) will discuss "Overcoming the Challenges of Batch Normalization in Federated Learning."
Please register for our mailing list at bit.ly/3WVplLU.
5
351
📢: The 118th FLOW talk is on Wednesday (10th July) at **1 pm UTC**.
Xiaowen Jiang (CISPA) will discuss "Fast Proximal-Point methods for Federated Optimization."
Please register to our mailing list: bit.ly/3WVplLU.
📢: The 117th FLOW talk is on Wednesday (12th June) at **5 pm UTC**.
Kumar Kshitij Patel (TTIC) will discuss "Revisiting the Convergence Theory for Local SGD and the Role of Personalization."
Please register to our mailing list: bit.ly/3WVplLU.
📢: The 116th FLOW talk is on Wednesday (27th March) at **1 pm UTC**.
Grigory Malinovsky (KAUST) will discuss "Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously."
Please register to our mailing list: bit.ly/3WVplLU.
📢: The 115th FLOW talk is on Wednesday (11th March) at **5 pm UTC**.
Mariel Werner (UC Berkeley) will discuss "Provably Personalized and Robust Federated Learning ."
Please register to our mailing list: bit.ly/3WVplLU.
📢: The 114th FLOW talk is on Wednesday (6th March) at **5 pm UTC**.
Xinyi Xu (NUS) will discuss "Fairness and Incentives for Data Sharing and Collaborative Learning."
Please register to our mailing list: bit.ly/3WVplLU.























